Improved runoff forecasting based on time-varying model averaging method and deep learning

• Published in: PloS one Vol. 17; no. 9; p. e0274004
• Main Authors: Ran, Jinlou, Cui, Yang, Xiang, Kai, Song, Yuchen
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 15.09.2022; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Analysis; Biology and Life Sciences; Computer and Information Sciences; Correlation analysis; Deep Learning; Dynamic models; Dynamic stability; Earth Sciences; Evaluation; Flood predictions; Floods; Forecasting; Forecasts and trends; Hydrologic cycle; Hydrology; Machine learning; Methods; Modelling; Monthly rainfall; Monthly runoff; Physical Sciences; Prediction models; Probability; Rain; Rainfall; Research and Analysis Methods; Runoff; Runoff forecasting; Simulation; Time series; Uncertainty; Water Movements; Weather forecasting; China; Huaihe River

In order to improve the accuracy and stability of runoff prediction. This study proposed a dynamic model averaging method with Time-varying weight (TV-DMA). Using this method, an integrated prediction model framework for runoff prediction was constructed. The framework determines the main variables...